Rag And Retrieval easy
Your product requires every RAG answer to include clickable source citations that users can verify. How should those citations be produced?
- A Ask the LLM to recall the URL of the source it originally learned each fact from in training.
- B After generation, run a web search on the answer text and link the top-ranked search result.
- C Embed the final answer text and cite whichever indexed chunk lies nearest to it in vector space.
- D Pass retrieved chunks with IDs, have the model cite those IDs, and map IDs to source links.
Answer: D. Pass retrieved chunks with IDs, have the model cite those IDs, and map IDs to source links.
**Citations must point at retrieved spans** the model actually saw, so tagging chunks with IDs ties each claim to verifiable evidence; the tradeoff is extra prompt structure and validating that cited IDs exist. Option C is tempting but matches the generated text, which may be hallucinated, to a chunk the model never used. Option A fails because models cannot reliably cite from memory and often invent URLs.
One system design question a day, with spaced repetition so the ones you miss come back.
Get the appRelated questions
- You must index 100M chunks using a 3,072-dimension embedding in fp32, served from RAM via HNSW. The raw vectors alone take about 1.2 TB before graph overhead. You need to cut memory several-fold while losing at most a point or two of recall@10. Which approach fits?
- A multi-tenant SaaS app stores all tenants in one vector index with a tenant_id field. Queries fetch the top 20 chunks by similarity and then drop chunks from other tenants. Small tenants often get 0-2 results. Why does this happen, and what is the fix?
- Runbooks are split into fixed 300-token chunks with no overlap. When a procedure step starts near the end of one chunk and finishes in the next, answers come back incomplete. What is the lowest-cost fix?
- Your offline eval shows recall@5 of 92% on a labeled set, so the gold passage is in the context for nearly every question. Yet human graders mark 35% of answers wrong, and the wrong answers often ignore or contradict the gold passage. Where should the team invest next?
- A runbook RAG system uses fixed 500-token chunks with no overlap. Users who ask for a multi-step recovery procedure get answers that stop at step 4 of 9, and retrieval logs show the top hit ends mid-procedure. What is the most targeted fix?
- Policy documents live in a CMS. A nightly job embeds and inserts new documents into the vector index. Users keep getting answers that cite policies which were deleted or replaced weeks ago. What is the root cause and fix?